Viewing enriched Twitter post
👀Perception Test: a benchmark for evaluating the perception and reasoning skills of multimodal models. It uses real-world videos to define tasks that require understanding of memory, patterns, physics, and semantics across visual, audio, and text. https://t.co/rZ9VFkjquM https://t.co/5yl802Fkuy
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1585276772391784448/media_0.jpg?",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1585276772391784448/media_0.jpg?",
"type": "photo",
"filename": "media_0.jpg"
}
],
"downloaded_to_supabase": true,
"processed_at": "2025-08-14T07:00:00Z"
}{
"type": "tweet",
"id": "1585276772391784448",
"url": "https://x.com/paperswithdata/status/1585276772391784448",
"twitterUrl": "https://twitter.com/paperswithdata/status/1585276772391784448",
"text": "👀Perception Test: a benchmark for evaluating the perception and reasoning skills of multimodal models. \n\nIt uses real-world videos to define tasks that require understanding of memory, patterns, physics, and semantics across visual, audio, and text.\n\nhttps://t.co/rZ9VFkjquM https://t.co/5yl802Fkuy",
"source": "Twitter for iPhone",
"retweetCount": 2,
"replyCount": 0,
"likeCount": 14,
"quoteCount": 0,
"viewCount": 0,
"createdAt": "Wed Oct 26 14:26:50 +0000 2022",
"lang": "en",
"bookmarkCount": 3,
"isReply": false,
"inReplyToId": null,
"conversationId": "1585276772391784448",
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "paperswithdata",
"url": "https://x.com/paperswithdata",
"twitterUrl": "https://twitter.com/paperswithdata",
"id": "1381544381509947393",
"name": "Papers with Datasets",
"isVerified": false,
"isBlueVerified": false,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1381624499624378372/YiVaI1-m_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1381544381509947393/1618241029",
"description": "",
"location": "",
"followers": 16865,
"following": 1,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Mon Apr 12 09:47:43 +0000 2021",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 133,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 234,
"statusesCount": 284,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [],
"profile_bio": {
"description": "Keep up with the latest machine learning datasets from @paperswithcode. Follow for daily updates.",
"entities": {
"description": {
"user_mentions": [
{
"id_str": "0",
"indices": [
55,
70
],
"name": "",
"screen_name": "paperswithcode"
}
]
},
"url": {
"urls": [
{
"display_url": "paperswithcode.com/datasets",
"expanded_url": "https://paperswithcode.com/datasets",
"indices": [
0,
23
],
"url": "https://t.co/a0cEQU8PX3"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"display_url": "pic.twitter.com/5yl802Fkuy",
"expanded_url": "https://twitter.com/paperswithdata/status/1585276772391784448/photo/1",
"ext_media_availability": {
"status": "Available"
},
"features": {
"all": {
"tags": [
{
"name": "Adrià Recasens",
"screen_name": "arecasens",
"type": "user",
"user_id": "7318592"
},
{
"name": "Mateusz Malinowski",
"screen_name": "MateuszOnAI",
"type": "user",
"user_id": "872839257735475202"
},
{
"name": "Carl Doersch",
"screen_name": "CarlDoersch",
"type": "user",
"user_id": "852856132632797184"
},
{
"name": "Antoine Miech",
"screen_name": "antoine77340",
"type": "user",
"user_id": "158768450"
},
{
"name": "张郡麟",
"screen_name": "JunlinZhang_",
"type": "user",
"user_id": "3884269582"
},
{
"name": "Yusuf Aytar",
"screen_name": "yusufaytar",
"type": "user",
"user_id": "198316717"
},
{
"name": "joao carreira",
"screen_name": "joaocarreira",
"type": "user",
"user_id": "22306308"
}
]
},
"large": {},
"orig": {}
},
"id_str": "1585276334330241026",
"indices": [
275,
298
],
"media_key": "3_1585276334330241026",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARYACG1KlmACCgACFgAI00kXEAAAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABFgAIbUqWYAIKAAIWAAjTSRcQAAAA",
"media_key": "3_1585276334330241026"
}
},
"media_url_https": "https://pbs.twimg.com/media/FgAIbUqWYAIFm5y.jpg",
"original_info": {
"focus_rects": [
{
"h": 672,
"w": 1200,
"x": 0,
"y": 0
},
{
"h": 675,
"w": 675,
"x": 263,
"y": 0
},
{
"h": 675,
"w": 592,
"x": 304,
"y": 0
},
{
"h": 675,
"w": 338,
"x": 431,
"y": 0
},
{
"h": 675,
"w": 1200,
"x": 0,
"y": 0
}
],
"height": 675,
"width": 1200
},
"sizes": {
"large": {
"h": 675,
"w": 1200
}
},
"type": "photo",
"url": "https://t.co/5yl802Fkuy"
}
]
},
"card": null,
"place": {},
"entities": {
"urls": [
{
"display_url": "paperswithcode.com/dataset/percep…",
"expanded_url": "https://paperswithcode.com/dataset/perception-test",
"indices": [
251,
274
],
"url": "https://t.co/rZ9VFkjquM"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"article": null
}